10 papers
Dreaming in Code for Curriculum Learning in Open-Ended Worlds
Konstantinos Mitsides, Maxence Faldor, Antoine Cully
Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent advances have utilized foundation models t…
Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversity
Hannah Janmohamed, Maxence Faldor, Thomas Pierrot +1
In a variety of domains, from robotics to finance, Quality-Diversity algorithms have been used to generate collections of both diverse and high-performing solutions. Multi-Objectiv…
Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Robert Tjarko Lange, Qi Sun, Aaditya Prasad +3
Recent advances in large language models (LLMs) demonstrate their effectiveness in scaling test-time compute for software engineering tasks. However, these approaches often focus o…
From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity
Luca Grillotti, Lisa Coiffard, Oscar Pang +2
Autonomous skill discovery aims to enable robots to acquire diverse behaviors without explicit supervision. Learning such behaviors directly on physical hardware remains challengin…
A Path to Universal Neural Cellular Automata
Gabriel Béna, Maxence Faldor, Dan F. M. Goodman +1
Cellular automata have long been celebrated for their ability to generate complex behaviors from simple, local rules, with well-known discrete models like Conway's Game of Life pro…
CAX: Cellular Automata Accelerated in JAX
Maxence Faldor, Antoine Cully
Cellular automata have become a cornerstone for investigating emergence and self-organization across diverse scientific disciplines. However, the absence of a hardware-accelerated…